RESUMEN
In order to protect intangible cultural heritage and promote outstanding cultural works, this article introduces innovative research on Shen Embroidery using convolutional neural networks. The dataset of Shen Embroidery was preprocessed to augment the data required for experimentation. Moreover, the approach of transfer learning was introduced to fine-tune the recognition network. Specifically, Spatial Pyramid Pooling (SPP) is employed by replacing the avg pool in the MobileNet V1 network, achieving the fusion of local and global features. The experimental results showed that the improved MobileNet V1 achieved a recognition accuracy of 98.45%, which was 2.3% higher than the baseline MobileNet V1 network. The experiments demonstrated that the improved convolutional neural network can efficiently recognize Shen Embroidery and provide technical support for the intelligent development of intangible cultural heritage.
RESUMEN
Optimizing the heat treatment procedure with 13 mm diameter 38Si7 spring steel is critical for developing high-performance, low-cost, large spring steel for railway clips. The effects of quenching temperature, holding time, tempering temperature, and tempering time on the microstructure and mechanical properties were investigated using an orthogonal experiment, designed with four factors and three levels. The best heat treatment settings were explored, as well as the variation laws of mechanical properties, decarburization behavior, and fracture morphology. The results demonstrated that quenching temperature and tempering temperature had the most impact on plasticity and tempering temperature, while time had the most effect on strength. The optimized heat treatment schemes made the elongation increase by up to 106% and the reduction in area increase by up to 67%, compared with the standard BS EN 10089-2002, and there were mixed fractures caused by ductility and brittleness. The fracture tests showed a good performance of 20.2 GPa·%, and the heat treatment processes' minimum decarburization depth of 93.4 µm was determined. The optimized process would obtain stronger plastic deposition and better decarburization performance. The microstructure was simply lightly tempered martensite, and the matrix still retained the acicular martensite. The optimal heat treatment process is quenching at 900 °C for 30 min (water cooling), followed by tempering at 430 °C for 60 min (air cooling). The research led to a solution for increasing the overall mechanical characteristics and decreasing the surface decarburization of 38Si7 spring steel with a diameter of 13 mm, and it set the foundation for increasing the mass production of railway clips of this size.
